Optimizing interaction flows

Abstract

Methods, apparatus, systems, computing devices, computing entities, and/or the like for optimizing interaction flows. For example, upon receiving an inbound interaction, the interaction is routed to either a baseline interaction flow or one of a plurality of experimental interaction flows. Using one or more target metrics, the experimental interaction flows can be monitored and further configured to optimize the interaction flows and parameters.

The invention claimed is: 
     
       1. A computer-implemented method for optimizing interaction flows, the method comprising:
 receiving, via one or more processors, an inbound interaction, wherein the inbound interaction is selected from the group consisting of a voice-based interaction and a textual-based interaction; 
 determining, via the one or more processors, whether to route the inbound interaction to a baseline interaction flow or to a first experimental interaction flow of a plurality of experimental interaction flows based at least in part on a configurable distribution ratio, wherein (a) the baseline interaction flow comprises a plurality of baseline interaction nodes and at least one defined path for executing each of the plurality baseline interaction nodes, (b) each of the plurality of experimental interaction flows comprises a plurality of experimental interaction nodes and at least one defined path for executing each of the plurality of experimental interaction nodes, and (c) the configurable distribution ratio defines the distribution of inbound interactions for the baseline interaction flow and the first experimental interaction flow; 
 responsive to determining to route the inbound interaction to the first experimental interaction flow based at least in part on the configurable distribution ratio, routing, via the one or more processors, the inbound interaction to the first experimental interaction flow; 
 after routing the inbound interaction to the first experimental interaction flow, automatically determining, via the one or more processors, that the first experimental interaction flow satisfies a threshold for a target metric; and 
 responsive to automatically determining that the first experimental interaction flow satisfies the threshold for the target metric, committing, via the one or more processors, the first experimental interaction flow as the baseline interaction flow, thereby changing the distribution ratio for the first experimental interaction flow. 
 
     
     
       2. The computer-implemented method of  claim 1 , wherein the target metric is selected from the group consisting of an abandonment rate, an authentication rate, and an interaction time. 
     
     
       3. The computer-implemented method of  claim 1 , wherein each of the plurality of experimental interaction nodes comprises one or more parameters. 
     
     
       4. The computer-implemented method of  claim 1 , wherein each experimental interaction flow is stored as an experimental interaction flow configuration. 
     
     
       5. The computer-implemented method of  claim 1 , wherein each experimental interaction flow configuration is pushed to a runtime environment, generated in a machine-readable format, and handles inbound interactions. 
     
     
       6. The computer-implemented method of  claim 1  further comprising: collecting baseline interaction flow data; and for each experimental interaction flow, collecting experimental interaction flow data. 
     
     
       7. A computer program product comprising a non-transitory computer readable medium having computer program instructions stored therein, the computer program instructions when executed by a processor, cause the processor to:
 receive an inbound interaction, wherein the inbound interaction is selected from the group consisting of a voice-based interaction and a textual-based interaction; 
 determine whether to route the inbound interaction to a baseline interaction flow or to a first experimental interaction flow of a plurality of experimental interaction flows based at least in part on a configurable distribution ratio, wherein (a) the baseline interaction flow comprises a plurality of baseline interaction nodes and at least one defined path for executing each of the plurality baseline interaction nodes, (b) each of the plurality of experimental interaction flows comprises a plurality of experimental interaction nodes and at least one defined path for executing each of the plurality of experimental interaction nodes, and (c) the configurable distribution ratio defines the distribution of inbound interactions for the baseline interaction flow and the first experimental interaction flow; 
 responsive to determining to route the inbound interaction to the first experimental interaction flow based at least in part on the configurable distribution ratio, route the inbound interaction to the first experimental interaction flow; 
 after routing the inbound interaction to the first experimental interaction flow, automatically determine that the first experimental interaction flow satisfies a threshold for a target metric; and 
 responsive to automatically determining that the first experimental interaction flow satisfies the threshold for the target metric, commit the first experimental interaction flow as the baseline interaction flow, thereby changing the distribution ratio for the first experimental interaction flow. 
 
     
     
       8. The computer program product of  claim 7 , wherein the target metric is selected from the group consisting of an abandonment rate, an authentication rate, and an interaction time. 
     
     
       9. The computer program product of  claim 7 , wherein each of the plurality of experimental interaction nodes comprises one or more parameters. 
     
     
       10. The computer program product of  claim 7 , wherein each experimental interaction flow is stored as an experimental interaction flow configuration. 
     
     
       11. The computer program product of  claim 7 , wherein each experimental interaction flow configuration is pushed to a runtime environment, generated in a machine-readable format, and handles inbound interactions. 
     
     
       12. The computer program product of  claim 7 , wherein the computer program instructions when executed by a processor, further cause the processor to:
 collect baseline interaction flow data; and 
 for each experimental interaction flow, collect experimental interaction flow data. 
 
     
     
       13. A computing system comprising a non-transitory computer readable storage medium and one or more processors, the computing system configured to:
 receive an inbound interaction, wherein the inbound interaction is selected from the group consisting of a voice-based interaction and a textual-based interaction; 
 determine whether to route the inbound interaction to a baseline interaction flow or to a first experimental interaction flow of a plurality of experimental interaction flows based at least in part on a configurable distribution ratio, wherein (a) the baseline interaction flow comprises a plurality of baseline interaction nodes and at least one defined path for executing each of the plurality baseline interaction nodes, (b) each of the plurality of experimental interaction flows comprises a plurality of experimental interaction nodes and at least one defined path for executing each of the plurality of experimental interaction nodes, and (c) the configurable distribution ratio defines the distribution of inbound interactions for the baseline interaction flow and the first experimental interaction flow; 
 responsive to determining to route the inbound interaction to the first experimental interaction flow based at least in part on the configurable distribution ratio, route the inbound interaction to the first experimental interaction flow; 
 after routing the inbound interaction to the first experimental interaction flow, automatically determine that the first experimental interaction flow satisfies a threshold for a target metric; and 
 responsive to automatically determining that the first experimental interaction flow satisfies the threshold for the target metric, commit the first experimental interaction flow as the baseline interaction flow, thereby changing the distribution ratio for the first experimental interaction flow. 
 
     
     
       14. The computing system of  claim 13 , wherein the target metric is selected from the group consisting of an abandonment rate, an authentication rate, and an interaction time. 
     
     
       15. The computing system of  claim 13 , wherein each of the plurality of experimental interaction nodes comprises one or more parameters. 
     
     
       16. The computing system of  claim 13 , wherein each experimental interaction flow is stored as an experimental interaction flow configuration. 
     
     
       17. The computing system of  claim 13 , wherein each experimental interaction flow configuration is pushed to a runtime environment, generated in a machine-readable format, and handles inbound interactions. 
     
     
       18. The computing system of  claim 13 , wherein the computing system is further configured to:
 collect baseline interaction flow data; and 
 for each experimental interaction flow, collect experimental interaction flow data.